Why do I not see as many additions to the destination table as a I see record loaded in a sync

The number of records loaded in a sync and the number of additions to the destination table may not always match due to the type of data synchronization you are using in Airbyte. If you are using incremental data synchronization, when you modify a record in the source system and then perform a sync, an updated version of the record will be copied from the source and appended to the raw table and the final table in the destination. However, even though the source only contains two records, both the raw and normalized destination tables contain three records each. This is because both the current and the previous version of the record with an id of 2 will be stored in each destination table. This could be why you are seeing fewer additions to the destination table than records loaded in a sync. [source](https://airbyte.com/tutorials/incremental-data-synchronization#step-6) If you are using full refresh data synchronization, the entire source table is appended into the destination. Additionally, only the data from the current and the previous sync have been normalized. This could also be why you are seeing fewer additions to the destination table than records loaded in a sync. [source](https://airbyte.com/tutorials/full-data-synchronization#step-8) If you are using Change Data Capture (CDC) synchronization, all of the intermediate states for each record have been captured and are stored in the destination. This is different from non-CDC incremental replication, in which only the state of the records in the source table at the moment the sync was executed was captured, and all intermediate states were lost. [source](https://airbyte.com/tutorials/incremental-change-data-capture-cdc-replication) Lastly, if you are using Refresh and Remove Records Syncs, only data that was newly synced since the refresh was initiated will be displayed in the destination’s final tables. [source](https://docs.airbyte.com/operator-guides/refreshes#refresh-and-remove-records) Therefore, the type of data synchronization you are using could be why you are not seeing as many additions to the destination table as you see records loaded in a sync.

difference between records extrated and loaded

Sorry @Murilo Fugazzotto, I'm not sure what you mean. Please try again. 👋

@kapa.ai - what’s the difference between record extrated and record loaded

In the context of Airbyte, a record is a single unit of data, often known as a "row". This could be a row in a table in a relational database, a line in a file, or a unit of data returned from an API ([source](https://docs.airbyte.com/using-airbyte/core-concepts#record)). When we talk about a record being "extracted", we are referring to the process of retrieving the record from the source system. This is the first step in the ELT (Extract, Load, Transform) process that Airbyte follows. The extracted data is sent to the destination as a single JSON blob, where it remains unmodified ([source](https://airbyte.com/tutorials/full-data-synchronization#step-1)). On the other hand, a record being "loaded" refers to the process of inserting the extracted data into the destination system. This is the second step in the ELT process. The loaded data is the raw, unmodified data that has been extracted from the source system and inserted into the destination system ([source](https://docs.airbyte.com/connector-development/ux-handbook#strongly-favor-elt-over-etl)). In the context of Airbyte's Job History, "Records emitted" refers to the number of records that have been extracted from the source system and sent to the platform orchestrator process. "Records committed" refers to the number of records that have been successfully persisted to permanent storage in the destination system ([source](https://github.com/airbytehq/airbyte/issues/28732)). In summary, the extraction of a record refers to the retrieval of the record from the source system, while the loading of a record refers to the insertion of that record into the destination system.